Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 5 May 2022 03:11:32 +0200
From:   "Jason A. Donenfeld" <Jason@zx2c4.com>
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Borislav Petkov <bp@alien8.de>,
        LKML <linux-kernel@vger.kernel.org>, x86@kernel.org,
        Filipe Manana <fdmanana@suse.com>, linux-crypto@vger.kernel.org
Subject: Re: [patch 3/3] x86/fpu: Make FPU protection more robust
Message-ID: <YnMkRLcxczMxdE5z@zx2c4.com>
References: <Ym/sHqKqmLOJubgE@zn.tnic>
 <87k0b4lydr.ffs@tglx>
 <YnDwjjdiSQ5Yml6E@hirez.programming.kicks-ass.net>
 <87fslpjomx.ffs@tglx>
 <YnKh96isoB7jiFrv@zx2c4.com>
 <87czgtjlfq.ffs@tglx>
 <YnLOXZp6WgH7ULVU@zx2c4.com>
 <87wnf1huwj.ffs@tglx>
 <YnMRwPFfvB0RlBow@zx2c4.com>
 <87mtfwiyqp.ffs@tglx>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <87mtfwiyqp.ffs@tglx>
Precedence: bulk

Hi Thomas,

On Thu, May 05, 2022 at 02:55:58AM +0200, Thomas Gleixner wrote:
> > So if truly the only user of this is random.c as of 5.18 (is it? I'm
> > assuming from a not very thorough survey...), and if the performance
> > boost doesn't even exist, then yeah, I think it'd make sense to just get
> > rid of it, and have kernel_fpu_usable() return false in those cases.
> >
> > I'll run some benchmarks on a little bit more hardware in representative
> > cases and see.
> 
> Find below a combo patch which makes use of strict softirq serialization
> for the price of not supporting the hardirq FPU usage. 

Thanks, I'll give it a shot in the morning (3am) when trying to do a
more realistic benchmark. But just as a synthetic thing, I ran the
numbers in kBench900 and am getting:

     generic:    430 cycles per call
       ssse3:    315 cycles per call
      avx512:    277 cycles per call

for a single call to the compression function, which is the most any of
those mix_pool_bytes() calls do from add_{input,disk}_randomness(), on
Tiger Lake, using RDPMC from kernel space.

This _doesn't_ take into account the price of calling kernel_fpu_begin().
That's a little hard to bench synthetically by running it in a loop and
taking medians because of the lazy restoration. But that's an indication
anyway that I should be looking at the cost of the actual function as
its running in random.c, rather than the synthetic test. Will keep this
thread updated.

Jason